Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Spiegel Online

Browse Source
This commit is contained in:
Kovid Goyal 2013-11-10 08:21:52 +05:30
parent a28b690f42
commit 16088aeb0e
1 changed files with 51 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
recipes/spiegelde.recipe
View File

@ -6,12 +6,16 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
spiegel.de
'''
import time, re
from contextlib import closing
from calibre import as_unicode
from calibre.web.feeds import feed_from_xml, Feed
from calibre.web.feeds.news import BasicNewsRecipe
class Spiegel_ger(BasicNewsRecipe):
title = 'Spiegel Online - German'
__author__ = 'Darko Miletic'
description = "Immer die neueste Meldung auf dem Schirm, sekundenaktuell und uebersichtlich: Mit dem RSS-Angebot von SPIEGEL ONLINE entgeht Ihnen keine wichtige Meldung mehr, selbst wenn Sie keinen Internet-Browser geoeffnet haben. Sie koennen unsere Nachrichten-Feeds ganz einfach abonnieren - unkompliziert, kostenlos und nach Ihren persoenlichen Themen-Vorlieben."
description = "Immer die neueste Meldung auf dem Schirm, sekundenaktuell und uebersichtlich: Mit dem RSS-Angebot von SPIEGEL ONLINE entgeht Ihnen keine wichtige Meldung mehr, selbst wenn Sie keinen Internet-Browser geoeffnet haben. Sie koennen unsere Nachrichten-Feeds ganz einfach abonnieren - unkompliziert, kostenlos und nach Ihren persoenlichen Themen-Vorlieben." # noqa
publisher = 'SPIEGEL ONLINE Gmbh'
category = 'SPIEGEL ONLINE, DER SPIEGEL, Nachrichten, News,Dienste, RSS, RSS, Feedreader, Newsfeed, iGoogle, Netvibes, Widget'
oldest_article = 7
@ -20,9 +24,18 @@ class Spiegel_ger(BasicNewsRecipe):
lang = 'de-DE'
no_stylesheets = True
use_embedded_content = False
auto_cleanup = True
auto_cleanup_keep = '//*[@id="spArticleTopAsset"]'
encoding = 'cp1252'
keep_only_tags = [
dict(name='h2', attrs={'class':'article-title'}),
dict(id=['js-article-top-wide-asset', 'js-article-column']),
]
remove_tags = [
dict(attrs={'class':lambda x: x and 'asset-html-box' in x.split()}),
dict(attrs={'class':lambda x: x and 'article-social-bookmark' in x.split()}),
dict(attrs={'class':lambda x: x and 'article-newsfeed-box' in x.split()}),
dict(attrs={'class':lambda x: x and 'article-comments-box' in x.split()}),
dict(attrs={'class':lambda x: x and 'article-functions-bottom' in x.split()}),
]
conversion_options = {
'comment' : description
@ -31,10 +44,42 @@ class Spiegel_ger(BasicNewsRecipe):
, 'language' : lang
}
feeds = [(u'Spiegel Online', u'http://www.spiegel.de/schlagzeilen/index.rss')]
def get_article_url(self, *args):
url = BasicNewsRecipe.get_article_url(self, *args).replace('#', '/#')
ai = re.search(r'ai=(\d+)', url).group(1)
soup = self.index_to_soup(url)
a = soup.find('a', href=lambda x: x and ai in x)
return 'http://www.spiegel.de' + a['href']
def parse_feeds(self):
title, url = self.feeds[0]
self.report_progress(0, _('Fetching feed')+' %s...'%(title if title else url))
parsed_feeds = []
try:
with closing(self.browser.open(url)) as s:
raw = s.read()
raw = raw.replace(b'<guid>http://www.spiegel.de</guid>', b'')
parsed_feeds.append(feed_from_xml(raw, title=title, log=self.log, oldest_article=self.oldest_article,
max_articles_per_feed=self.max_articles_per_feed,
get_article_url=self.get_article_url))
if (self.delay > 0):
time.sleep(self.delay)
except Exception as err:
feed = Feed()
msg = 'Failed feed: %s'%(title if title else url)
feed.populate_from_preparsed_feed(msg, [])
feed.description = as_unicode(err)
parsed_feeds.append(feed)
self.log.exception(msg)
remove = [f for f in parsed_feeds if len(f) == 0 and
self.remove_empty_feeds]
for f in remove:
parsed_feeds.remove(f)
return parsed_feeds